INDEX

Explanations

versions of software or libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

rowsable

-0.16

rams

-0.16

ãĤµãĥ¼

-0.14

ifo

-0.14

ĵ¨

-0.14

verbosity

-0.14

 kháº£o

-0.13

mere

-0.13

iless

-0.13

andom

-0.13

POSITIVE LOGITS

0.15

Hem

0.15

Ð¸Ð¹

0.15

Guard

0.14

undi

0.14

writes

0.14

 Ellison

0.14

keh

0.14

 back

0.14

 Quest

0.14

Activations Density 0.023%

versions of software or libraries

No Comments

No Known Activations