INDEX

Explanations

references to political party affiliations, specifically related to Democrats and Republicans

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

echa

-0.15

emen

-0.15

 Vine

-0.14

laces

-0.14

UNE

-0.14

erdale

-0.14

icmp

-0.14

iday

-0.14

naments

-0.14

finity

-0.13

POSITIVE LOGITS

0.16

-leaning

0.15

-only

0.15

Ð³Ð°Ð»Ñĸ

0.15

ollect

0.15

ãĥ¬ãĥ³

0.14

orum

0.14

%%%%

0.14

 ASCII

0.14

Activations Density 0.019%

references to political party affiliations, specifically related to Democrats and Republicans

No Comments

No Known Activations