INDEX

Explanations

expressions of dislike or negative feelings towards subjects or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ally

-0.15

essler

-0.15

cap

-0.15

orsch

-0.15

-0.14

aily

-0.14

pose

-0.14

 Rica

-0.14

ÏĨÏīÎ½

-0.14

POSITIVE LOGITS

rank

0.16

afen

0.14

akter

0.14

unist

0.14

 Shapiro

0.14

 ÐĴÐ¸ÐºÐ¸

0.14

bounce

0.13

.preview

0.13

 tuá»ķi

0.13

askell

0.13

Activations Density 0.023%

expressions of dislike or negative feelings towards subjects or concepts

No Comments

No Known Activations