INDEX

Explanations

references to voting and election-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ness

-0.18

ties

-0.17

side

-0.16

 Ð²Ð¾ÑĤ

-0.16

iates

-0.16

-0.15

iate

-0.15

loha

-0.15

ue

-0.15

ien

-0.15

POSITIVE LOGITS

 cast

0.18

 caster

0.18

cast

0.16

LU

0.15

 Cast

0.15

_cast

0.15

able

0.14

islav

0.14

ycastle

0.14

Activations Density 0.019%

references to voting and election-related activities

No Comments

No Known Activations