INDEX

Explanations

discussions about various factors influencing decisions or analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

rox

-0.17

/commons

-0.16

ignum

-0.16

otti

-0.15

tÃŃ

-0.13

ÏĦÎ¬

-0.13

etooth

-0.13

 Validate

-0.13

VICE

-0.13

æŁ±

-0.13

POSITIVE LOGITS

 factors

0.82

 factor

0.73

 Factors

0.68

Factors

0.59

-factor

0.58

factor

0.57

 Factor

0.57

Factor

0.56

 ÑĦÐ°ÐºÑĤÐ¾ÑĢ

0.54

_factor

0.51

Activations Density 0.216%

discussions about various factors influencing decisions or analyses

No Comments

No Known Activations