INDEX

Explanations

specific formatting structures or syntax used in programming or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

IFS

-0.16

ÙĨØ¯ÛĮ

-0.15

 meis

-0.15

 Tits

-0.15

((__

-0.14

Ĥæķ°

-0.14

å·¨

-0.14

áº¡p

-0.14

ipsis

-0.14

plusplus

-0.14

POSITIVE LOGITS

 True

0.17

Pep

0.16

 Cond

0.15

/u

0.15

 None

0.15

æļ

0.15

Mez

0.15

 Wild

0.14

amel

0.14

Activations Density 0.016%

specific formatting structures or syntax used in programming or coding contexts

No Comments

No Known Activations