INDEX

Explanations

references to distinct groups or categories within a broader context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

oki

-0.15

irl

-0.14

caffold

-0.13

nable

-0.13

 Freak

-0.13

urat

-0.13

nÄħ

-0.13

 Interr

-0.13

ernet

-0.13

ehr

-0.13

POSITIVE LOGITS

 besides

0.19

mega

0.15

bes

0.14

cant

0.14

keley

0.14

wat

0.14

olini

0.14

 Duffy

0.14

wie

0.13

Activations Density 0.329%

references to distinct groups or categories within a broader context

No Comments

No Known Activations