INDEX

Explanations

terms associated with credibility

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Depot

-0.15

 Morrison

-0.14

ensive

-0.14

 Appalachian

-0.14

Kit

-0.14

ghest

-0.14

etto

-0.13

 ë©´

-0.13

ãĤīãģĦ

-0.13

anic

-0.13

POSITIVE LOGITS

bot

0.15

èĩ£

0.15

aders

0.14

chia

0.14

bot

0.14

iras

0.14

inya

0.14

jez

0.14

/latest

0.13

RACT

0.13

Activations Density 0.004%

terms associated with credibility

No Comments

No Known Activations