INDEX

Explanations

phrases that indicate future actions or offers of assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Heard

-0.18

 remembered

-0.15

imeo

-0.14

zn

-0.14

got

-0.14

aylor

-0.14

FormField

-0.14

FIELDS

-0.14

ochen

-0.14

zek

-0.13

POSITIVE LOGITS

 find

0.21

 finds

0.19

 finde

0.18

inds

0.17

 fine

0.17

 finer

0.16

/latest

0.16

 Minds

0.15

pel

0.15

see

0.15

Activations Density 0.045%

phrases that indicate future actions or offers of assistance

No Comments

No Known Activations