INDEX

Explanations

Code/technical text

np_max-act · gemini-2.0-flash

The neuron fires on the character sequence “omorph” (as in “isomorphisms”), i.e. it detects the “-omorph” substring.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ipv

-0.07

ียง

-0.06

정을

-0.06

�

-0.06

 هنوز

-0.06

 Shutdown

-0.06

ONGL

-0.06

ampled

-0.06

سون

-0.06

ναν

-0.06

POSITIVE LOGITS

WhatsApp

0.07

_project

0.06

.QRect

0.06

assoc

0.06

_direct

0.06

.str

0.06

/archive

0.06

Archive

0.06

.gz

0.06

Activations Density 0.299%

Code/technical text

The neuron fires on the character sequence “omorph” (as in “isomorphisms”), i.e. it detects the “-omorph” substring.

No Comments

No Known Activations