INDEX

Explanations

prominent nouns and names associated with specific notable topics or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

uan

-0.16

appa

-0.14

ped

-0.14

usu

-0.14

ServiceProvider

-0.14

ord

-0.14

aeper

-0.13

storm

-0.13

pherd

-0.13

spar

-0.13

POSITIVE LOGITS

.bz

0.16

illow

0.16

ksiyon

0.15

.Tween

0.15

0.14

fabs

0.13

.tk

0.13

à¤łà¤¨

0.13

uesta

0.13

ogne

0.13

Activations Density 0.076%

prominent nouns and names associated with specific notable topics or places

No Comments

No Known Activations