INDEX

Explanations

emotional expressions and references to listening or communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

elmet

-0.17

ieri

-0.17

isbury

-0.16

ilon

-0.15

braco

-0.15

ritel

-0.14

ierz

-0.14

aucoup

-0.14

iag

-0.14

à¸¸à¹ī

-0.14

POSITIVE LOGITS

 listen

0.91

 hear

0.89

 listening

0.88

 listened

0.81

 hearing

0.81

 listens

0.79

 heard

0.79

 Listen

0.78

listen

0.77

 Hear

0.76

Activations Density 0.452%

emotional expressions and references to listening or communication

No Comments

No Known Activations