INDEX

Explanations

references to academic journals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

igram

-0.15

ern

-0.15

SN

-0.14

etal

-0.14

PDF

-0.14

 natural

-0.13

_uniform

-0.13

 Ãĸr

-0.13

alk

-0.13

bis

-0.13

POSITIVE LOGITS

AGER

0.21

à¸¢à¸¡

0.17

 volume

0.16

 volumes

0.16

opolitan

0.16

nad

0.15

LOPT

0.15

volume

0.15

YSIS

0.15

ADER

0.14

Activations Density 0.056%

references to academic journals

No Comments

No Known Activations