INDEX

Explanations

occurrences of specific non-Latin characters

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

cheon

-0.16

iode

-0.15

bens

-0.14

ovenant

-0.13

altura

-0.13

tal

-0.13

REFERRED

-0.13

cona

-0.13

eldorf

-0.13

Gur

-0.13

POSITIVE LOGITS

 analyzer

0.32

Analyzer

0.32

 Token

0.32

 tokenizer

0.31

/token

0.30

 Analyzer

0.29

 token

0.29

tokenizer

0.29

Tokenizer

0.28

 TOKEN

0.28

Activations Density 0.009%

occurrences of specific non-Latin characters

No Comments

No Known Activations

occurrences of specific non-Latin characters

No Comments

No Known Activations