INDEX

Explanations

instances of the word "controversial" in various contexts

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

eyh

-0.18

aptop

-0.17

ullo

-0.16

odal

-0.15

bih

-0.15

TURE

-0.15

ansen

-0.15

Ð°Ð½ÑģÐ¸

-0.14

ë¥

-0.14

ullah

-0.14

POSITIVE LOGITS

ly

0.18

uns

0.15

ocrates

0.15

 vigil

0.15

 Kata

0.14

 Marsh

0.14

Ago

0.14

overs

0.14

 skins

0.14

ute

0.14

Activations Density 0.004%

instances of the word "controversial" in various contexts

No Comments

No Known Activations