INDEX

Explanations

terms related to data, time, and combined experiences or efforts

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

ownik

-0.17

vez

-0.16

ardi

-0.15

enstein

-0.15

weg

-0.15

imuth

-0.15

åĬ

-0.14

isper

-0.14

ushman

-0.14

platz

-0.14

POSITIVE LOGITS

urer

0.16

upp

0.16

oha

0.14

Cast

0.14

 circ

0.14

 Cast

0.14

SYM

0.14

Î³ÎºÎ±

0.14

onda

0.14

tap

0.14

Activations Density 0.002%

terms related to data, time, and combined experiences or efforts

No Comments

No Known Activations