INDEX

Explanations

phrases indicating a record of past performance or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

cki

-0.17

lsen

-0.15

vale

-0.15

 Wein

-0.15

ssf

-0.14

rum

-0.14

iola

-0.14

licas

-0.14

 Compar

-0.14

krom

-0.14

POSITIVE LOGITS

 preced

0.17

/portfolio

0.16

 precedent

0.16

 background

0.16

Ped

0.16

(history

0.15

 track

0.15

rove

0.15

lify

0.15

/history

0.15

Activations Density 0.031%

phrases indicating a record of past performance or experiences

No Comments

No Known Activations