INDEX

Explanations

references to significant titles, names, or identifiers within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

_simps

-0.14

_variance

-0.14

achen

-0.14

ix

-0.14

Ops

-0.14

unity

-0.14

Powered

-0.14

plusplus

-0.13

 screws

-0.13

ÃŃ

-0.13

POSITIVE LOGITS

quo

0.16

 Knot

0.15

ÑĢÑĥÑĩ

0.15

iol

0.15

goo

0.15

bas

0.14

svp

0.14

ataire

0.13

dÄ±

0.13

Activations Density 0.001%

references to significant titles, names, or identifiers within a text

No Comments

No Known Activations