INDEX

Explanations

references to sociopolitical structures and dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ingen

-0.16

anger

-0.15

fol

-0.14

oise

-0.14

ROLS

-0.14

rites

-0.14

ardy

-0.14

odel

-0.13

cription

-0.13

 incident

-0.13

POSITIVE LOGITS

resher

0.15

omu

0.14

Î¹Î²

0.14

ãģķãĤī

0.14

ophobic

0.14

rank

0.14

iscal

0.14

 Ð´ÐµÑĢÐ¶

0.14

íģ¼

0.13

agher

0.13

Activations Density 0.127%

references to sociopolitical structures and dynamics

No Comments

No Known Activations