INDEX

Explanations

mathematical expressions and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

UAL

-0.17

koli

-0.16

 hors

-0.15

uyá»ĥn

-0.14

bung

-0.14

ÑıÐº

-0.14

gri

-0.14

gr

-0.14

cles

-0.14

ãĥ¼ãĤ¹

-0.14

POSITIVE LOGITS

gis

0.17

aise

0.14

URRE

0.14

ady

0.14

roj

0.13

 sacram

0.13

åĦĢ

0.13

Î´Îµ

0.13

CJK

0.13

orio

0.13

Activations Density 0.017%

mathematical expressions and symbols

No Comments

No Known Activations