INDEX

Explanations

negative or conditional phrases indicating uncertainty or refusal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

izzo

-0.17

unk

-0.15

ÐµÐ½Ðµ

-0.14

ownik

-0.14

 cellspacing

-0.14

é¡¿

-0.13

duk

-0.13

reesome

-0.13

ADIUS

-0.13

PN

-0.13

POSITIVE LOGITS

 protest

0.20

 react

0.20

 move

0.19

 movement

0.19

bud

0.18

 speak

0.17

 reacting

0.17

 reacts

0.17

 reaction

0.17

React

0.17

Activations Density 0.346%

negative or conditional phrases indicating uncertainty or refusal

No Comments

No Known Activations