INDEX

Explanations

references to mountains or mountainous landscapes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ujet

-0.16

aname

-0.15

ureau

-0.15

uche

-0.15

agli

-0.14

KER

-0.14

ĵn

-0.14

heet

-0.14

 ãģı

-0.14

Ðĥ

-0.13

POSITIVE LOGITS

 Mountains

0.16

ides

0.14

/high

0.14

ains

0.14

 mountains

0.14

rej

0.14

amet

0.14

bine

0.13

 summit

0.13

von

0.13

Activations Density 0.060%

references to mountains or mountainous landscapes

No Comments

No Known Activations