INDEX

Explanations

references to software compatibility and applications across different versions and devices

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

PAD

-0.15

assen

-0.15

asse

-0.14

ennes

-0.14

pag

-0.14

jur

-0.14

issan

-0.14

isses

-0.14

alo

-0.14

iti

-0.14

POSITIVE LOGITS

ushima

0.17

oty

0.17

OKIE

0.17

apolis

0.16

lider

0.14

ASI

0.14

fÃ¶r

0.14

/ns

0.14

 Wend

0.14

GRP

0.14

Activations Density 0.175%

references to software compatibility and applications across different versions and devices

No Comments

No Known Activations