INDEX

Explanations

aspects of background and contextual details related to individuals or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

fore

-0.15

 Willi

-0.15

.hm

-0.15

like

-0.14

tuk

-0.14

Sas

-0.14

 Giov

-0.14

bourg

-0.13

hem

-0.13

POSITIVE LOGITS

ÑĩÐ¸Ðµ

0.18

Ã±os

0.16

ientes

0.15

ãģĭãģĳ

0.15

ismet

0.14

çµµ

0.14

/vnd

0.14

acher

0.14

pNet

0.14

iginal

0.13

Activations Density 0.044%

aspects of background and contextual details related to individuals or situations

No Comments

No Known Activations