INDEX

Explanations

articles and prepositions in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

åĩ¡

-0.17

-0.14

emi

-0.14

ãĤĥ

-0.14

 Monroe

-0.14

ahoma

-0.14

Ð¾Ð»Ð¾Ð´

-0.14

alls

-0.14

_PHP

-0.14

angling

-0.14

POSITIVE LOGITS

yre

0.19

0.16

oric

0.16

orney

0.16

á»¥

0.15

Ð³Ñĥ

0.15

erb

0.14

rych

0.14

 Fish

0.14

itest

0.14

Activations Density 0.056%

articles and prepositions in the text

No Comments

No Known Activations