INDEX

Explanations

instances of the word "in" and related phrase structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

auc

-0.17

andles

-0.16

emain

-0.15

lescope

-0.15

 Hearth

-0.15

arcer

-0.15

eeper

-0.14

iple

-0.14

inges

-0.14

uÃŃ

-0.14

POSITIVE LOGITS

bed

0.16

 sharedInstance

0.15

 traffic

0.15

 Corner

0.14

 corner

0.14

 chairs

0.14

_bw

0.14

 Jacques

0.14

 chair

0.14

aya

0.14

Activations Density 0.174%

instances of the word "in" and related phrase structures

No Comments

No Known Activations