INDEX

Explanations

references to various public broadcasting stations and media entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ibold

-0.18

zcze

-0.16

resher

-0.15

 Pale

-0.14

asso

-0.14

deaux

-0.14

 Himself

-0.14

aupt

-0.14

ries

-0.13

ritten

-0.13

POSITIVE LOGITS

áº¥p

0.15

unner

0.14

chemy

0.14

ãĤ¶

0.14

Runner

0.14

 Rugby

0.13

uckle

0.13

ãĥ¥ãĥ¼

0.13

pector

0.13

coop

0.13

Activations Density 0.493%

references to various public broadcasting stations and media entities

No Comments

No Known Activations