INDEX

Explanations

indicators of notable achievements or prominent figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

.habbo

-0.15

ileo

-0.14

lein

-0.14

MEM

-0.14

jis

-0.14

-0.13

ÙĨØ¯ÙĬØ©

-0.13

å¤§äºº

-0.13

duk

-0.13

èĻİ

-0.13

POSITIVE LOGITS

dera

0.17

arsi

0.16

teki

0.15

/jav

0.14

eron

0.14

actable

0.14

éĢł

0.14

Cop

0.14

rete

0.13

 notas

0.13

Activations Density 0.027%

indicators of notable achievements or prominent figures

No Comments

No Known Activations