INDEX

Explanations

references to job performance and related tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

SSI

-0.16

ibold

-0.16

allen

-0.16

isher

-0.16

ients

-0.15

pdata

-0.15

aggio

-0.14

ence

-0.14

/up

-0.14

cky

-0.14

POSITIVE LOGITS

manship

0.18

sworth

0.17

forc

0.16

bed

0.16

aday

0.16

stead

0.15

lessness

0.14

/goto

0.14

sters

0.14

fillType

0.14

Activations Density 0.050%

references to job performance and related tasks

No Comments

No Known Activations