INDEX

Explanations

expressions indicating possibility or necessity

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

LoginForm

-0.15

ê¶ģ

-0.15

yclopedia

-0.14

odiac

-0.14

ebo

-0.14

Ð¾ÑĤÑĮ

-0.14

neau

-0.14

-0.13

POSITIVE LOGITS

rid

0.14

Orth

0.14

gc

0.14

zbo

0.13

å§ĳ

0.13

omu

0.13

late

0.13

Miss

0.13

ition

0.13

rium

0.13

Activations Density 0.122%

expressions indicating possibility or necessity

No Comments

No Known Activations