INDEX

Explanations

special characters or symbols that often represent unique identifiers in various contexts

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

éĺ²

-0.16

 assurances

-0.15

ä¿Ŀè¯ģ

-0.15

prevent

-0.15

 aseg

-0.15

 assures

-0.14

ä¿Ŀéļľ

-0.14

 éĺ²

-0.14

 Ð³Ð°ÑĢÐ°Ð½

-0.14

 combating

-0.13

POSITIVE LOGITS

 explore

0.22

 listen

0.22

 browse

0.21

 practise

0.21

 enrol

0.21

 visit

0.21

 immer

0.21

 watch

0.20

 spend

0.20

 download

0.20

Activations Density 0.044%

special characters or symbols that often represent unique identifiers in various contexts

No Comments

No Known Activations