INDEX

Explanations

references to George W. Bush and his administration

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

ijn

-0.15

idis

-0.15

ohn

-0.15

ook

-0.15

ifik

-0.14

HV

-0.14

achers

-0.14

 palate

-0.14

jal

-0.13

.palette

-0.13

POSITIVE LOGITS

kud

0.17

,");↵

0.16

omnia

0.15

 environ

0.15

_contin

0.14

azen

0.14

vero

0.14

en

0.14

orient

0.13

 continu

0.13

Activations Density 0.010%

references to George W. Bush and his administration

No Comments

No Known Activations

references to George W. Bush and his administration

No Comments

No Known Activations