INDEX

Explanations

terms related to sand

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

stal

-0.15

FAG

-0.14

hood

-0.14

/pub

-0.14

hof

-0.13

mgr

-0.13

acon

-0.13

StringUtil

-0.13

 Giang

-0.13

borg

-0.13

POSITIVE LOGITS

iest

0.19

 dust

0.15

jez

0.15

-paper

0.15

itect

0.15

igger

0.14

Sep

0.14

æ²Ļ

0.14

ehler

0.14

enaire

0.14

Activations Density 0.035%

terms related to sand

No Comments

No Known Activations