INDEX

Explanations

specific dates or years mentioned within the text

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

ixon

-0.15

},'

-0.14

rical

-0.14

FORMATION

-0.14

ider

-0.14

usan

-0.14

ieten

-0.14

igar

-0.14

-0.13

sts

-0.13

POSITIVE LOGITS

ona

0.17

ãĥĨãĥ«

0.14

mith

0.14

OSH

0.14

unas

0.14

ottes

0.14

isin

0.13

ltr

0.13

ONA

0.13

pine

0.13

Activations Density 0.017%

specific dates or years mentioned within the text

No Comments

No Known Activations