INDEX

Explanations

references to multiple entities, configurations, or identities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ajor

-0.15

onth

-0.15

cken

-0.15

 directly

-0.15

 Kramer

-0.14

amics

-0.14

ibli

-0.14

illard

-0.13

 fashioned

-0.13

sm

-0.13

POSITIVE LOGITS

 equally

0.20

 versions

0.20

 VERSION

0.19

 voices

0.19

 birden

0.19

 simultaneous

0.19

 competing

0.19

 identities

0.18

çīĪæľ¬

0.18

 worlds

0.18

Activations Density 0.209%

references to multiple entities, configurations, or identities

No Comments

No Known Activations