INDEX

Explanations

technical terminology and concepts related to data processing and analysis in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ulp

-0.16

 Slater

-0.15

wind

-0.14

anker

-0.14

.newaxis

-0.14

Å¡t

-0.14

dez

-0.14

isu

-0.14

dag

-0.13

Bag

-0.13

POSITIVE LOGITS

FAULT

0.16

 Dash

0.15

 management

0.15

razier

0.15

paring

0.15

æŃ

0.15

rol

0.15

ÏįÎ½

0.14

aldi

0.14

æĽ¸é¤¨

0.14

Activations Density 0.298%

technical terminology and concepts related to data processing and analysis in various fields

No Comments

No Known Activations