INDEX

Explanations

words that signify distinctions or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ves

-0.17

Ĭ

-0.15

 Blank

-0.15

iant

-0.15

inet

-0.15

Toe

-0.15

INET

-0.15

 oblig

-0.15

 Francisco

-0.15

POSITIVE LOGITS

SelectionMode

0.16

NotSupportedException

0.16

ardown

0.15

_Tis

0.15

ÑħÐ°

0.15

amespace

0.15

 addCriterion

0.15

á»£

0.15

roupon

0.14

ednou

0.14

Activations Density 0.000%

words that signify distinctions or comparisons

No Comments

No Known Activations