INDEX

Explanations

instances of numerical data and specific proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

uder

-0.17

ucas

-0.16

eldon

-0.15

ÃŃÅĻ

-0.15

èĹį

-0.15

wid

-0.15

inf

-0.15

 widest

-0.14

bin

-0.14

POSITIVE LOGITS

assel

0.15

modelName

0.15

uli

0.14

 drafting

0.14

rics

0.14

aler

0.14

TEX

0.14

(^

0.14

anca

0.14

ormsg

0.14

Activations Density 0.118%

instances of numerical data and specific proper nouns

No Comments

No Known Activations