INDEX

Explanations

phrases indicating specific locations or regions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

enha

-0.14

vature

-0.14

Fro

-0.14

Ð¼ÐµÑģÑĤ

-0.14

ipse

-0.14

"label

-0.14

ÏĥÏĦÎµ

-0.13

seau

-0.13

ritz

-0.13

aternity

-0.13

POSITIVE LOGITS

walls

0.15

.Strict

0.14

asl

0.14

 walls

0.14

à¥įà¤Ĺà¤¤

0.14

 Walls

0.13

adas

0.13

abc

0.13

urre

0.13

liers

0.13

Activations Density 0.037%

phrases indicating specific locations or regions

No Comments

No Known Activations