INDEX

Explanations

references to various types of equipment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

tail

-0.16

ucas

-0.16

ore

-0.15

emez

-0.15

ect

-0.14

pane

-0.14

çĿ

-0.14

/rc

-0.14

icro

-0.13

quina

-0.13

POSITIVE LOGITS

/software

0.19

/services

0.16

urator

0.15

arel

0.15

ponge

0.15

Å©i

0.15

ils

0.15

ovenant

0.15

rels

0.15

Activations Density 0.019%

references to various types of equipment

No Comments

No Known Activations