INDEX

Explanations

repetitive phrases or contextually significant markers 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

uz

-0.19

idis

-0.15

uses

-0.14

ther

-0.14

and

-0.14

ter

-0.14

ader

-0.14

icon

-0.13

 Cave

-0.13

uv

-0.13

POSITIVE LOGITS

 alone

0.22

is

0.21

 fact

0.20

 situation

0.17

has

0.17

fact

0.17

isa

0.17

 trend

0.16

 latter

0.16

 itself

0.16

Activations Density 0.182%

repetitive phrases or contextually significant markers in the text

No Comments

No Known Activations