INDEX

Explanations

requests for action or attention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

FTA

-0.16

 Ð¡ÑĥÐ´

-0.14

opard

-0.14

ajes

-0.14

udes

-0.14

uffers

-0.14

zac

-0.14

gth

-0.14

lero

-0.14

à¸µà¸¢à¸§à¸ģ

-0.14

POSITIVE LOGITS

idden

0.16

WithOptions

0.15

adu

0.15

0.14

otland

0.14

 Balk

0.14

ooke

0.14

icina

0.14

Activations Density 0.000%

requests for action or attention

No Comments

No Known Activations