INDEX

Explanations

references to entities or people related to various situations and conditions

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

oria

-0.15

iques

-0.15

vez

-0.15

 volume

-0.15

 Morrison

-0.14

.ci

-0.14

itzer

-0.14

å°¼äºļ

-0.14

dot

-0.14

amin

-0.14

POSITIVE LOGITS

stru

0.15

igel

0.15

macen

0.15

LEEP

0.15

tran

0.14

SB

0.14

Ð»ÑĥÐ³

0.14

usan

0.14

oteca

0.14

Activations Density 0.070%

references to entities or people related to various situations and conditions

No Comments

No Known Activations