INDEX

Explanations

negations and expressions of disapproval or reluctance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ricks

-0.17

avou

-0.16

 proh

-0.15

quette

-0.15

IELDS

-0.15

-coordinate

-0.14

ÑĩÐ°Ñģ

-0.14

prit

-0.14

-0.13

ignum

-0.13

POSITIVE LOGITS

aign

0.14

 accepting

0.14

_EXT

0.14

Ø§Ø²Ùĩ

0.14

á»ķ

0.14

 Grimm

0.14

icker

0.13

adan

0.13

 reliance

0.13

 Sharp

0.13

Activations Density 0.123%

negations and expressions of disapproval or reluctance

No Comments

No Known Activations