INDEX

Explanations

References to geographical locations and movements

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

 scope

-0.16

uin

-0.15

trinsic

-0.15

leur

-0.15

ivo

-0.14

ano

-0.14

ombine

-0.14

 appointment

-0.14

 task

-0.14

Nas

-0.13

POSITIVE LOGITS

 Chandler

0.16

Sharper

0.15

udad

0.15

 Surveillance

0.15

luk

0.14

ENCH

0.14

Ã¢y

0.14

radan

0.14

unpack

0.14

.EndsWith

0.13

Activations Density 0.106%

References to geographical locations and movements

No Comments

No Known Activations