INDEX

Explanations

references to statistics and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

_TYPED

-0.15

urette

-0.15

lobals

-0.14

.Uint

-0.14

åĽ³

-0.14

 homes

-0.14

 cá»Ń

-0.14

dro

-0.14

 Consolid

-0.14

gid

-0.14

POSITIVE LOGITS

rana

0.15

Eid

0.14

ISCO

0.14

jk

0.14

icken

0.14

$LANG

0.14

 numberWith

0.14

Cay

0.13

 vagina

0.13

aste

0.13

Activations Density 0.017%

references to statistics and numerical data

No Comments

No Known Activations