INDEX

Explanations

references to geographic locations and photography-related terms

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

aub

-0.17

 thunder

-0.17

 mainland

-0.16

.ns

-0.15

ubu

-0.15

PCI

-0.15

ais

-0.15

AMA

-0.14

adata

-0.14

çĸ

-0.14

POSITIVE LOGITS

Lun

0.15

 Ð¿ÑĸÐ´Ñģ

0.14

iams

0.14

emic

0.14

antas

0.14

holm

0.14

 edil

0.14

FirstChild

0.14

 Foley

0.13

Activations Density 0.023%

references to geographic locations and photography-related terms

No Comments

No Known Activations