INDEX

Explanations

names of public figures and officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

\OptionsResolver

-0.15

avl

-0.15

avana

-0.15

avor

-0.15

unos

-0.14

andy

-0.14

aval

-0.14

 AttributeSet

-0.14

avia

-0.14

åĿĽ

-0.14

POSITIVE LOGITS

iser

0.18

igo

0.16

uts

0.16

ersh

0.15

erset

0.15

itsu

0.15

ĥ

0.14

iam

0.14

enta

0.14

Activations Density 0.007%

names of public figures and officials

No Comments

No Known Activations