INDEX

Explanations

references to religious concepts and teachings

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

Not in Any Lists

No Comments

Negative Logits

ibold

-0.16

isia

-0.16

ISA

-0.14

Ã¦r

-0.14

kj

-0.14

aisal

-0.14

ÏħÏĥ

-0.14

stp

-0.13

ensem

-0.13

POSITIVE LOGITS

jal

0.16

okit

0.16

eds

0.15

nik

0.15

 Reform

0.15

oks

0.14

pread

0.14

opher

0.14

Ð»Ð°Ð³

0.14

Activations Density 0.678%

references to religious concepts and teachings

No Comments

No Known Activations