INDEX

Explanations

terms related to measurement and evaluation criteria

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ager

-0.17

ãĥĸãĥª

-0.17

ican

-0.15

odie

-0.15

elm

-0.15

alink

-0.15

.pix

-0.15

ello

-0.14

ica

-0.14

jsx

-0.14

POSITIVE LOGITS

lesia

0.16

isÃŃ

0.16

tach

0.15

ãģĹãĤĩãģĨ

0.15

tam

0.15

rosse

0.15

tas

0.15

erap

0.14

ewe

0.14

thur

0.14

Activations Density 0.007%

terms related to measurement and evaluation criteria

No Comments

No Known Activations