INDEX

Explanations

online communities

np_max-act · gemini-2.0-flash

Tokens that indicate the assistant referring to itself or giving a refusal/explanatory disclaimer (e.g., self-identity and refusal phrases).

oai_token-act-pair · gpt-5-mini Triggered by @vetterc0

self-referential disclaimers where the assistant identifies itself as an AI language model and explains limitations or refusal to comply.

oai_token-act-pair · gpt-5 Triggered by @vetterc0

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_*

-0.06

 كم

-0.06

casts

-0.06

Border

-0.06

�

-0.06

pre

-0.06

 výj

-0.06

mix

-0.06

POSITIVE LOGITS

 leash

0.07

LOOK

0.06

 Huckabee

0.06

 capable

0.06

TransparentColor

0.06

(savedInstanceState

0.06

 waist

0.06

 mặc

0.06

 już

0.06

 Marie

0.06

Activations Density 0.034%

online communities

Tokens that indicate the assistant referring to itself or giving a refusal/explanatory disclaimer (e.g., self-identity and refusal phrases).

self-referential disclaimers where the assistant identifies itself as an AI language model and explains limitations or refusal to comply.

No Comments

No Known Activations