INDEX

Explanations

references to downloadable or printable materials and related functions

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

Dys

-0.14

rane

-0.14

leck

-0.13

oland

-0.13

etail

-0.13

 Gent

-0.13

geg

-0.13

 ZemÄĽ

-0.13

nce

-0.13

icie

-0.13

POSITIVE LOGITS

essenger

0.17

ubbo

0.15

itar

0.15

Ø±ÙģØª

0.15

avern

0.14

zÄħ

0.14

inen

0.14

unal

0.14

orm

0.14

Activations Density 0.269%

references to downloadable or printable materials and related functions

No Comments

No Known Activations