INDEX

Explanations

numerical values and references to software deployment processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ã¡li

-0.17

ummer

-0.16

oulos

-0.15

anca

-0.15

Ã©gor

-0.14

utan

-0.14

amina

-0.14

pal

-0.14

ieber

-0.14

ozor

-0.14

POSITIVE LOGITS

zel

0.17

ENTS

0.14

ypo

0.14

Vet

0.14

abin

0.14

rl

0.14

ersist

0.13

wis

0.13

idl

0.13

 Pins

0.13

Activations Density 0.037%

numerical values and references to software deployment processes

No Comments

No Known Activations