INDEX

Explanations

phrases that describe quantities or measurements within a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

igt

-0.16

ÏĢÎ¿

-0.16

Ã½t

-0.15

KEN

-0.15

ying

-0.15

arken

-0.15

ngÃ¶r

-0.14

culo

-0.14

esy

-0.14

_pieces

-0.13

POSITIVE LOGITS

izzle

0.18

è©±

0.17

Ã³m

0.16

udad

0.16

ixels

0.16

anel

0.15

aver

0.15

udo

0.14

riz

0.14

uda

0.14

Activations Density 0.068%

phrases that describe quantities or measurements within a technical context

No Comments

No Known Activations