INDEX

Explanations

references to measurements and quantities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

inged

-0.16

.cgi

-0.16

otted

-0.15

ngÃ¶r

-0.14

ughs

-0.14

allee

-0.14

ìķĦìĦľ

-0.14

.GetText

-0.14

 Butler

-0.14

-0.13

POSITIVE LOGITS

ares

0.15

ä¸įäºĨ

0.15

mus

0.14

ziel

0.14

chner

0.14

nda

0.13

.habbo

0.13

çľī

0.13

umba

0.13

-Core

0.13

Activations Density 0.038%

references to measurements and quantities in various contexts

No Comments

No Known Activations