INDEX

Explanations

mentions of the word "Aston" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

es

-0.18

tings

-0.17

idal

-0.17

ual

-0.16

tn

-0.15

ting

-0.15

udio

-0.15

usal

-0.14

sie

-0.14

POSITIVE LOGITS

ishing

0.23

ishment

0.23

ished

0.17

ishments

0.16

ndef

0.16

exion

0.15

unft

0.15

edef

0.15

 Parallel

0.15

mars

0.15

Activations Density 0.009%

mentions of the word "Aston" and its variations

No Comments

No Known Activations