INDEX

Explanations

elements related to DOM manipulation or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ÙĪØ¬Ùĩ

-0.15

plet

-0.15

dro

-0.14

adro

-0.14

çĬ¬

-0.14

uchar

-0.14

her

-0.14

houette

-0.14

iar

-0.14

POSITIVE LOGITS

egal

0.16

urret

0.15

anned

0.15

Ø±Ø¶

0.14

 Ø§ÙĦØ¹Ùħ

0.14

 cans

0.14

ittest

0.13

tiles

0.13

iri

0.13

ances

0.13

Activations Density 0.046%

elements related to DOM manipulation or attributes

No Comments

No Known Activations