INDEX

Explanations

references to popular culture, particularly in TV shows and movies

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

//{{

-0.16

ÃĹ↵↵

-0.16

Î±Î½Î´

-0.15

LOOR

-0.14

PIPE

-0.14

OLEAN

-0.13

-navigation

-0.13

 Measure

-0.13

"""č↵

-0.13

AuthProvider

-0.13

POSITIVE LOGITS

egov

0.20

woord

0.15

 Restricted

0.14

ouncer

0.14

roller

0.14

isia

0.13

Commission

0.13

 Recruitment

0.13

 Schl

0.13

 Rookie

0.13

Activations Density 1.112%

references to popular culture, particularly in TV shows and movies

No Comments

No Known Activations