INDEX

Explanations

references and mentions of the English language, particularly 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

omial

-0.18

jit

-0.15

gart

-0.15

tura

-0.14

ÑħÐ¸

-0.14

hey

-0.14

aday

-0.14

gings

-0.14

unctuation

-0.14

à¸±à¸ĵà¸ĳ

-0.13

POSITIVE LOGITS

-speaking

0.19

izar

0.17

spe

0.15

ridge

0.15

/XML

0.14

bower

0.14

izador

0.14

klÃ¤r

0.14

arily

0.14

ermen

0.14

Activations Density 0.020%

references and mentions of the English language, particularly in various contexts

No Comments

No Known Activations