INDEX

Explanations

terms related to data structure manipulation and resource management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ifter

-0.15

noinspection

-0.15

.sap

-0.14

icity

-0.14

avr

-0.14

 kent

-0.14

orrow

-0.13

æĢ§çļĦ

-0.13

iciary

-0.13

voir

-0.13

POSITIVE LOGITS

avel

0.17

illon

0.17

otech

0.16

landa

0.16

AMP

0.15

kud

0.14

á»ĳc

0.13

 McCl

0.13

§

0.13

Ð¾ÐºÐ¾Ð»

0.13

Activations Density 0.494%

terms related to data structure manipulation and resource management

No Comments

No Known Activations