INDEX

Explanations

references to religious guidance and its implications for followers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

lip

-0.16

anse

-0.16

unde

-0.16

OLA

-0.16

afen

-0.16

ola

-0.15

semicolon

-0.14

ÅĻad

-0.13

uten

-0.13

CID

-0.13

POSITIVE LOGITS

izard

0.16

 Gardens

0.16

Ñľ

0.16

Our

0.15

 Associates

0.15

 disbelief

0.15

 Warner

0.15

 Allan

0.15

 Nous

0.15

Khu

0.14

Activations Density 0.026%

references to religious guidance and its implications for followers

No Comments

No Known Activations