INDEX

Explanations

references to Jewish history and anti-Semitism 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

iner

-0.17

ende

-0.17

OLS

-0.15

als

-0.14

igg

-0.14

iet

-0.14

ode

-0.14

vez

-0.14

ension

-0.14

IRS

-0.13

POSITIVE LOGITS

.Param

0.16

 ÐĴÐ¸ÐºÐ¸

0.15

ezier

0.15

\\/

0.15

imon

0.14

apus

0.14

å±ĭ

0.14

 Kahn

0.14

Activations Density 1.010%

references to Jewish history and anti-Semitism in various contexts

No Comments

No Known Activations