INDEX

Explanations

names and affiliations of researchers or authors in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

lesc

-0.16

eldorf

-0.16

illez

-0.15

stub

-0.15

incinn

-0.15

iola

-0.14

 Weiss

-0.14

.bias

-0.14

 alone

-0.14

blink

-0.14

POSITIVE LOGITS

 Piper

0.15

Sv

0.14

 selves

0.13

>>)

0.13

enance

0.13

 Stats

0.13

unp

0.13

 canned

0.13

 Dennis

0.12

 Alicia

0.12

Activations Density 0.065%

names and affiliations of researchers or authors in a scientific context

No Comments

No Known Activations