INDEX

Explanations

phrases that emphasize or rephrase a point

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ÙĪØ±Ø§ÙĨ

-0.15

amarin

-0.15

Î¯ÏĦ

-0.15

 addCriterion

-0.14

æĲį

-0.14

attered

-0.14

pch

-0.14

uder

-0.14

alon

-0.14

ãģĿãģĹãģ¦

-0.14

POSITIVE LOGITS

ç¼ĺ

0.16

 basically

0.16

 pretty

0.15

anges

0.15

 essentially

0.15

 normal

0.15

eder

0.15

0.14

 once

0.14

-await

0.14

Activations Density 0.073%

phrases that emphasize or rephrase a point

No Comments

No Known Activations