INDEX

Explanations

references to specific years and electoral events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 veto

-0.16

pictures

-0.15

ÑīÐ¸Ð½

-0.15

 replaced

-0.14

-plugins

-0.14

 streak

-0.14

zman

-0.14

cken

-0.13

 replacing

-0.13

Sig

-0.13

POSITIVE LOGITS

 Cunning

0.17

 RedirectTo

0.15

é¦Ļ

0.15

.svg

0.14

.cx

0.14

ael

0.14

atz

0.14

Ð°ÑĤÐºÑĥ

0.14

eger

0.14

 seats

0.14

Activations Density 0.008%

references to specific years and electoral events

No Comments

No Known Activations