INDEX

Explanations

references to language and translation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Ireland

-0.16

ox

-0.14

hana

-0.14

pron

-0.14

iph

-0.14

ully

-0.14

 intra

-0.14

 India

-0.14

 steam

-0.13

ilden

-0.13

POSITIVE LOGITS

 English

0.39

English

0.35

 Spanish

0.30

 english

0.29

 Hebrew

0.29

 languages

0.28

english

0.28

èĭ±è¯Ń

0.28

 Arabic

0.27

 Tiáº¿ng

0.27

Activations Density 0.134%

references to language and translation

No Comments

No Known Activations