INDEX

Explanations

common verbs and phrases indicating actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

åĿ¡

-0.15

ennai

-0.14

FLOAT

-0.14

.inline

-0.14

ãĥ³ãĤ¬

-0.13

Å¡e

-0.13

éłĵ

-0.13

atcher

-0.13

ÏĦÎ·ÏĤ

-0.13

POSITIVE LOGITS

 history

0.16

-ignore

0.15

_tac

0.15

history

0.14

bev

0.14

bia

0.14

 History

0.14

qu

0.14

 Doch

0.14

oled

0.13

Activations Density 0.003%

common verbs and phrases indicating actions or states

No Comments

No Known Activations