INDEX

Explanations

negative attributes or issues in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ady

-0.17

igner

-0.15

-Col

-0.15

ilder

-0.14

æ³ģ

-0.14

Highest

-0.14

 proxy

-0.13

aps

-0.13

ence

-0.13

afe

-0.13

POSITIVE LOGITS

ouz

0.16

ambi

0.16

/stdc

0.15

ABCDEFGHIJKLMNOP

0.15

udiant

0.14

icode

0.14

pane

0.14

ancia

0.14

alaria

0.14

assi

0.14

Activations Density 0.042%

negative attributes or issues in various contexts

No Comments

No Known Activations