INDEX

Explanations

numerical data and values from programming or data analysis contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

osti

-0.14

veau

-0.14

alo

-0.13

ch

-0.13

nox

-0.13

{?

-0.13

odef

-0.13

lab

-0.13

rene

-0.13

atch

-0.13

POSITIVE LOGITS

0.17

0.15

ONTAL

0.15

ffffffff

0.15

 Decomp

0.15

nan

0.14

ÂłE

0.14

usk

0.14

inspace

0.14

Activations Density 0.079%

numerical data and values from programming or data analysis contexts

No Comments

No Known Activations