INDEX

Explanations

phrases and elements related to numerical or statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Invariant

-0.16

CCI

-0.16

dyn

-0.15

æħİ

-0.15

illo

-0.15

loid

-0.15

StatusLabel

-0.15

)::

-0.15

Debugger

-0.14

odus

-0.14

POSITIVE LOGITS

ittel

0.16

 unic

0.16

uzzi

0.15

ellas

0.14

ousel

0.14

hol

0.14

nett

0.14

_ASCII

0.14

endo

0.14

untas

0.14

Activations Density 0.007%

phrases and elements related to numerical or statistical information

No Comments

No Known Activations