INDEX

Explanations

instances of comments or interactions in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 latter

-0.14

 favors

-0.14

Roe

-0.14

 McCorm

-0.13

oa

-0.13

 Cant

-0.13

 Anchor

-0.13

ÅĤo

-0.13

 Crud

-0.13

 favor

-0.13

POSITIVE LOGITS

kas

0.16

(#)

0.15

alars

0.14

omat

0.14

ICAST

0.14

 slik

0.13

eyle

0.13

ola

0.13

ibold

0.13

pla

0.13

Activations Density 0.012%

instances of comments or interactions in the text

No Comments

No Known Activations