INDEX

Explanations

questions and uncertainties expressed in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Cage

-0.16

iston

-0.16

tember

-0.16

-0.14

rosse

-0.14

gunakan

-0.14

obuf

-0.13

Lum

-0.13

istine

-0.13

ancock

-0.13

POSITIVE LOGITS

or

0.16

 Redemption

0.15

ior

0.15

RITE

0.14

onth

0.14

 backpage

0.14

quam

0.14

 EXIT

0.13

naw

0.13

borg

0.13

Activations Density 0.258%

questions and uncertainties expressed in the text

No Comments

No Known Activations