INDEX

Explanations

concepts related to evaluation and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ç»ıè¿ĩ

-0.13

 sÃ¡nh

-0.12

ìķ¤

-0.11

anded

-0.11

ÑĢÐ°Ñĩ

-0.11

assi

-0.11

Ìģt

-0.11

ozem

-0.11

oled

-0.11

asma

-0.11

POSITIVE LOGITS

 mentioned

0.79

 described

0.69

mentioned

0.68

 listed

0.65

 discussed

0.63

 outlined

0.58

 cited

0.56

 above

0.54

listed

0.52

 aforementioned

0.52

Activations Density 1.361%

concepts related to evaluation and decision-making processes

No Comments

No Known Activations