INDEX

Explanations

instances of pronouns and their associated actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

oppel

-0.15

opsis

-0.15

 Semester

-0.14

uzzi

-0.14

Ð²Ð¾

-0.14

KF

-0.14

Ã»

-0.14

bf

-0.13

Î¸ÎµÎ½

-0.13

stvo

-0.13

POSITIVE LOGITS

amen

0.16

atham

0.14

inding

0.14

à¹Ģà¸Ĺ

0.14

 cite

0.14

anted

0.14

dik

0.14

 Miss

0.14

REATE

0.14

Scoped

0.13

Activations Density 0.037%

instances of pronouns and their associated actions or states

No Comments

No Known Activations