INDEX

Explanations

geographical locations and place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

atte

-0.17

ouser

-0.15

 Kelvin

-0.15

IDI

-0.15

ady

-0.15

-0.14

 Russo

-0.14

arken

-0.14

Tob

-0.14

deviceId

-0.14

POSITIVE LOGITS

.gdx

0.17

CCR

0.15

geÃ§

0.15

apos

0.15

FromClass

0.15

oux

0.15

_gold

0.15

TRL

0.14

 WCHAR

0.14

Hora

0.14

Activations Density 0.067%

geographical locations and place names

No Comments

No Known Activations