INDEX

Explanations

references to specific product features and their technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

STANCE

-0.17

orraine

-0.16

queda

-0.14

aklÄ±

-0.14

inci

-0.14

isbury

-0.14

Å¯l

-0.14

ãĢħ

-0.14

enor

-0.14

achs

-0.14

POSITIVE LOGITS

isol

0.17

amiento

0.16

astos

0.16

(AP

0.16

(AL

0.15

.cfg

0.15

åĭ¢

0.15

(AT

0.14

asu

0.14

terra

0.14

Activations Density 1.424%

references to specific product features and their technical specifications

No Comments

No Known Activations