INDEX

Explanations

references to actions, relationships, and conditions involving strong connections or important entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

stead

-0.15

ê¶ģ

-0.15

agraph

-0.15

ABCDEFG

-0.15

CHANT

-0.15

assi

-0.15

.ColumnHeader

-0.14

agens

-0.14

OptionsResolver

-0.14

ÃŃas

-0.14

POSITIVE LOGITS

Ð°Ð²Ð°

0.15

auc

0.15

0.14

ewart

0.14

UIS

0.14

yles

0.14

NOT

0.14

ÑĥÑģÐ°

0.14

eger

0.14

Activations Density 0.001%

references to actions, relationships, and conditions involving strong connections or important entities

No Comments

No Known Activations