INDEX

Explanations

references to specific items or entities in a descriptive context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 double

-0.16

ither

-0.15

 just

-0.15

ington

-0.14

 Double

-0.14

just

-0.14

illard

-0.14

 Happ

-0.14

POSITIVE LOGITS

åħ±

0.16

åĿĽ

0.15

 playa

0.15

<TResult

0.14

ì´Ŀ

0.14

ZONE

0.14

comb

0.14

nesty

0.14

-share

0.14

 differ

0.13

Activations Density 0.223%

references to specific items or entities in a descriptive context

No Comments

No Known Activations