INDEX

Explanations

references to privacy policies and user agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ulong

-0.14

xca

-0.14

argar

-0.14

 potent

-0.14

cale

-0.14

etur

-0.13

OLF

-0.13

union

-0.13

 Hust

-0.13

 Holt

-0.13

POSITIVE LOGITS

0.15

isman

0.15

inned

0.15

pearance

0.14

-Ñı

0.14

.nano

0.14

ìĤ¬ìĿ´

0.13

@js

0.13

TemplateName

0.13

CONDS

0.13

Activations Density 0.031%

references to privacy policies and user agreements

No Comments

No Known Activations