INDEX

Explanations

elements or terms related to species classification and taxonomy

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

gas

-0.15

asco

-0.15

á»įc

-0.15

uiten

-0.15

Alive

-0.14

omers

-0.14

clud

-0.13

á»ĵi

-0.13

inity

-0.13

inh

-0.13

POSITIVE LOGITS

ael

0.17

OLE

0.14

Ì£

0.13

¶Į

0.13

AAC

0.13

 mines

0.13

 Marion

0.13

 shouts

0.13

preferences

0.13

 Kinder

0.13

Activations Density 0.056%

elements or terms related to species classification and taxonomy

No Comments

No Known Activations