INDEX

Explanations

key locations and references to individuals or groups related to immigration and personal stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ERSHEY

-0.14

_DECL

-0.14

AFP

-0.14

rightness

-0.14

nton

-0.14

zeÅĦ

-0.14

esiz

-0.13

ellig

-0.13

acock

-0.13

edla

-0.13

POSITIVE LOGITS

 instead

0.17

ires

0.16

undef

0.15

RW

0.14

asu

0.14

ivor

0.14

 Pays

0.14

ula

0.13

Pic

0.13

_expired

0.13

Activations Density 0.184%

key locations and references to individuals or groups related to immigration and personal stories

No Comments

No Known Activations