INDEX

Explanations

references to boarding activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

avig

-0.15

astics

-0.15

ored

-0.14

acha

-0.14

porno

-0.14

ÙĪÙĬØ³

-0.14

åĽ²

-0.14

GBT

-0.13

SO

-0.13

inux

-0.13

POSITIVE LOGITS

åĸľ

0.17

olk

0.16

0.15

wik

0.15

chr

0.15

Å¾ÃŃ

0.15

olle

0.15

Ħ

0.14

-lang

0.14

 boarding

0.14

Activations Density 0.006%

references to boarding activities

No Comments

No Known Activations