INDEX

Explanations

references to performance measurements or evaluations

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

pin

-0.17

orna

-0.16

gy

-0.16

ner

-0.16

ward

-0.15

apor

-0.15

lian

-0.14

spo

-0.14

iff

-0.14

POSITIVE LOGITS

anagan

0.17

placer

0.15

WER

0.15

Ð¾Ñħ

0.15

razier

0.15

over

0.14

IGHL

0.14

ãĤĵãģ¨

0.14

eÄį

0.14

å¡ļ

0.14

Activations Density 0.041%

references to performance measurements or evaluations

No Comments

No Known Activations