INDEX

Explanations

references to specific brands and products in the context of consumerism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Å¡en

-0.15

lingen

-0.15

inspace

-0.15

Äįet

-0.14

glas

-0.14

://%

-0.14

Ã¶h

-0.14

heel

-0.14

etto

-0.14

pesan

-0.14

POSITIVE LOGITS

oven

0.15

mar

0.14

UTH

0.14

Âł

0.14

Case

0.13

IGO

0.13

 Wool

0.13

uffman

0.13

ificador

0.12

 Wyatt

0.12

Activations Density 0.442%

references to specific brands and products in the context of consumerism

No Comments

No Known Activations