INDEX

Explanations

titles and names associated with publications or events, particularly relating to historical or academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

jh

-0.16

 Abram

-0.14

bern

-0.14

Abr

-0.14

nock

-0.14

teb

-0.14

ese

-0.14

.sol

-0.14

 tail

-0.13

å°¾

-0.13

POSITIVE LOGITS

£p

0.16

uito

0.16

aeda

0.15

rowsable

0.15

uhn

0.15

Î¼Î¯

0.15

-Clause

0.14

ITO

0.14

aja

0.14

igest

0.14

Activations Density 0.271%

titles and names associated with publications or events, particularly relating to historical or academic contexts

No Comments

No Known Activations