INDEX

Explanations

specific names or titles, likely related to film or personal identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

çĴĥ

-0.16

rych

-0.15

 zoekt

-0.15

isque

-0.15

Ã¦nd

-0.14

oubted

-0.14

uco

-0.14

isbury

-0.14

aleur

-0.14

aving

-0.14

POSITIVE LOGITS

dash

0.15

otes

0.15

ume

0.14

 pers

0.14

AINER

0.14

¯¼

0.14

 ALOG

0.13

oy

0.13

Jack

0.13

etsy

0.13

Activations Density 0.014%

specific names or titles, likely related to film or personal identifiers

No Comments

No Known Activations