INDEX

Explanations

numerical representations of quantities or counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Era

-0.15

raith

-0.15

isson

-0.15

 Acres

-0.15

iete

-0.15

 ÑĥÐ¶

-0.14

verting

-0.14

Ã¡v

-0.14

POSITIVE LOGITS

\Eloquent

0.16

ullan

0.16

.habbo

0.16

 Stam

0.15

tractive

0.14

cona

0.14

 illustr

0.14

 Weiss

0.14

urai

0.14

Kup

0.13

Activations Density 0.066%

numerical representations of quantities or counts

No Comments

No Known Activations