INDEX

Explanations

phrases expressing suggestions or recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

marvin

-0.19

.oauth

-0.16

adors

-0.16

spath

-0.15

ei

-0.15

 outs

-0.15

iw

-0.15

owi

-0.15

ouro

-0.15

 interracial

-0.14

POSITIVE LOGITS

quil

0.14

Å¼

0.14

ks

0.14

 Elim

0.14

jes

0.13

 Convenience

0.13

archy

0.13

jd

0.13

NT

0.13

uka

0.13

Activations Density 0.006%

phrases expressing suggestions or recommendations

No Comments

No Known Activations