INDEX

Explanations

references to comparisons and similarities between subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.16

 Alley

-0.16

atin

-0.15

ÑĢÐ¸Ñĩ

-0.15

-0.14

dess

-0.14

reau

-0.14

quine

-0.14

opia

-0.14

POSITIVE LOGITS

 nhau

0.21

 together

0.16

emens

0.16

ä¸Ģèµ·

0.15

retty

0.15

kip

0.14

mlin

0.14

ingly

0.14

roperties

0.14

ignKey

0.14

Activations Density 0.291%

references to comparisons and similarities between subjects

No Comments

No Known Activations