INDEX

Explanations

specific numerical values or identifiers related to measurements or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ð»Ð¸Ð·

-0.16

hone

-0.15

lisi

-0.15

 CallingConvention

-0.15

Baby

-0.15

baz

-0.15

iaux

-0.14

io

-0.14

 Honey

-0.14

POSITIVE LOGITS

ç¸

0.16

 folding

0.16

 Burk

0.15

 Burgess

0.15

 Rowe

0.15

 Garrison

0.15

 prophecy

0.15

UGE

0.15

æĤ

0.15

èį

0.15

Activations Density 0.006%

specific numerical values or identifiers related to measurements or assessments

No Comments

No Known Activations