INDEX

Explanations

affirmative or descriptive statements across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

opause

-0.16

soever

-0.15

eting

-0.14

beiten

-0.13

iler

-0.13

 dabei

-0.13

áº¥y

-0.13

ces

-0.13

oting

-0.13

ouver

-0.13

POSITIVE LOGITS

how

0.28

why

0.27

 where

0.27

why

0.19

how

0.19

How

0.19

 happening

0.18

 going

0.18

 Where

0.18

Why

0.18

Activations Density 0.092%

affirmative or descriptive statements across various contexts

No Comments

No Known Activations