INDEX

Explanations

unique names or proper nouns related to people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ixa

-0.16

alama

-0.14

Ø§Ø´

-0.14

ãĢģäºĮ

-0.14

LETTE

-0.14

_wheel

-0.14

mÃ©na

-0.14

Reuse

-0.14

 Baldwin

-0.13

ixin

-0.13

POSITIVE LOGITS

ActionCreators

0.15

Selectors

0.14

 beste

0.14

ronym

0.14

yte

0.14

-san

0.14

yat

0.13

empo

0.13

 himself

0.13

illet

0.13

Activations Density 0.079%

unique names or proper nouns related to people

No Comments

No Known Activations