INDEX

Explanations

references to academic publications or scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

.nano

-0.16

ģn

-0.16

eck

-0.14

urve

-0.14

luent

-0.14

 Mickey

-0.13

ë

-0.13

Â°E

-0.13

Pa

-0.13

 Album

-0.13

POSITIVE LOGITS

AMPL

0.15

warts

0.15

-spinner

0.14

aca

0.14

 shot

0.14

_kwargs

0.14

amos

0.14

 NONINFRINGEMENT

0.13

unk

0.13

reg

0.13

Activations Density 0.125%

references to academic publications or scientific research

No Comments

No Known Activations