INDEX

Explanations

various forms of identifying information such as names or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

bsite

-0.14

trag

-0.14

brtc

-0.14

Ìģc

-0.13

allon

-0.13

Ø²ÙħØ§ÙĨ

-0.13

 resil

-0.13

è¾°

-0.13

ÅĻÃŃm

-0.13

loys

-0.13

POSITIVE LOGITS

ians

0.14

alse

0.13

ete

0.13

[email

0.13

ease

0.13

 Worm

0.13

ãĥ§

0.13

pch

0.13

aukee

0.13

ascus

0.13

Activations Density 0.266%

various forms of identifying information such as names or entities

No Comments

No Known Activations