INDEX

Explanations

references to data sources and statistical claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

vens

-0.15

kin

-0.15

iasi

-0.14

 Ø¨Ø¯Ø§ÙĨ

-0.14

 advers

-0.14

egal

-0.14

ë¡

-0.14

agen

-0.14

POSITIVE LOGITS

ITOR

0.17

emann

0.14

ecided

0.14

-NLS

0.14

enticated

0.14

airo

0.14

ibri

0.14

ollah

0.14

/forum

0.13

AccessException

0.13

Activations Density 0.002%

references to data sources and statistical claims

No Comments

No Known Activations