INDEX

Explanations

all

np_max-act · gemini-2.0-flash

The neuron activates on user requests asking to list “all” of something—that is, quantifying list‐all prompts.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

กร

-0.07

 Flame

-0.07

.blogspot

-0.07

Tek

-0.07

 actual

-0.06

 valore

-0.06

 viene

-0.06

 alas

-0.06

 chief

-0.06

 بدان

-0.06

POSITIVE LOGITS

_rights

0.06

 güney

0.06

DSM

0.06

 ecstatic

0.06

.'.

0.06

(l

0.06

thead

0.06

Node

0.06

 topLevel

0.06

ــــ

0.06

Activations Density 0.034%

all

The neuron activates on user requests asking to list “all” of something—that is, quantifying list‐all prompts.

No Comments

No Known Activations