INDEX

Explanations

symbols and references associated with Jewish identity and iconography

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Ø§Ø±Ú©

-0.16

 Monter

-0.16

Ã²i

-0.15

èŃ·

-0.14

ayet

-0.14

æº

-0.14

rup

-0.14

DEST

-0.14

iforn

-0.14

upport

-0.14

POSITIVE LOGITS

lix

0.16

udos

0.15

uong

0.14

ullan

0.14

TD

0.14

 Bund

0.13

 prepar

0.13

atts

0.13

ear

0.13

Activations Density 0.084%

symbols and references associated with Jewish identity and iconography

No Known Activations