INDEX

Explanations

references to support or advocacy for specific political positions or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

lah

-0.16

lm

-0.15

 Ð¿ÑĢÐ¸Ð¼

-0.14

(éĩĳ

-0.14

scape

-0.14

flux

-0.14

proof

-0.13

'&#

-0.13

POSITIVE LOGITS

ouble

0.15

hlen

0.15

ovny

0.15

onec

0.14

uture

0.13

oun

0.13

 Humanities

0.13

 Polo

0.13

InChildren

0.13

Activations Density 0.014%

references to support or advocacy for specific political positions or groups

No Comments

No Known Activations