INDEX

Explanations

detailed descriptions of technical processes and elements in programming or medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 prob

-0.24

ÏģÏİ

-0.12

ÙĳØª

-0.12

 —↵

-0.12

 probs

-0.12

ç¨

-0.11

 ?><?

-0.11

ÑĢÐ°Ð¿

-0.11

Gow

-0.11

*((

-0.11

POSITIVE LOGITS

(-

0.75

`-

0.70

 negative

0.68

(-

0.66

[-

0.65

=-

0.61

 Negative

0.59

'-

0.59

"-

0.59

,-

0.58

Activations Density 0.870%

detailed descriptions of technical processes and elements in programming or medical contexts

No Comments

No Known Activations