INDEX

Explanations

affirmative statements or confirmations regarding services and capabilities

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

ittel

-0.17

esc

-0.17

antan

-0.15

 Barn

-0.13

Esp

-0.13

czy

-0.13

eless

-0.13

ej

-0.13

umba

-0.13

 queryInterface

-0.13

POSITIVE LOGITS

 trace

0.17

ordes

0.17

 Wick

0.16

 Trace

0.16

Trace

0.15

.df

0.15

veral

0.14

otland

0.14

trace

0.14

_trace

0.13

Activations Density 0.134%

affirmative statements or confirmations regarding services and capabilities

No Comments

No Known Activations