INDEX

Explanations

citations from various news sources and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ÐµÑĢÐ²

-0.18

.generated

-0.15

byte

-0.15

stime

-0.14

axon

-0.14

oid

-0.14

ime

-0.14

_nat

-0.13

andid

-0.13

ichert

-0.13

POSITIVE LOGITS

0.15

stad

0.14

mey

0.14

0.13

onda

0.13

itom

0.13

inas

0.13

æĿ¥ãģŁ

0.13

Reserved

0.13

Activations Density 0.088%

citations from various news sources and publications

No Comments

No Known Activations