INDEX

Explanations

references to outdoor spaces or activities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ystate

-0.19

DBG

-0.15

uras

-0.15

.nih

-0.15

insula

-0.14

 whisk

-0.14

Qed

-0.14

erable

-0.14

uitka

-0.14

æģµ

-0.14

POSITIVE LOGITS

 stead

0.17

avi

0.15

Lem

0.15

cg

0.15

 Pend

0.14

oodoo

0.14

 unlike

0.14

OLT

0.14

ivals

0.13

 basics

0.13

Activations Density 0.003%

references to outdoor spaces or activities

No Comments

No Known Activations