INDEX

Explanations

references to various retail or service chains

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

comed

-0.15

rale

-0.15

Î·Î½

-0.15

Ð»Ð°Ð´Ñĥ

-0.14

/goto

-0.14

ãĥ³ãĥĳ

-0.14

DirectoryName

-0.14

YNAMIC

-0.14

ÑĪÑĥ

-0.14

.metro

-0.13

POSITIVE LOGITS

argon

0.16

krit

0.16

rk

0.15

forg

0.15

 Hicks

0.15

yb

0.15

amount

0.15

acco

0.14

Gal

0.14

<<<<<<<

0.14

Activations Density 0.004%

references to various retail or service chains

No Comments

No Known Activations