INDEX

Explanations

references to biblical or religious symbolism and motifs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Benedict

-0.14

elix

-0.14

å¼ı

-0.14

onga

-0.14

 drowned

-0.14

³

-0.13

 Metro

-0.13

 Hass

-0.13

POSITIVE LOGITS

PFN

0.18

inton

0.15

iyim

0.15

noch

0.15

uco

0.14

raquo

0.14

 Williamson

0.14

frauen

0.13

 (!((

0.13

atform

0.13

Activations Density 0.418%

references to biblical or religious symbolism and motifs

No Comments

No Known Activations