INDEX

Explanations

terms related to software building and project management processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

di

-0.15

nten

-0.15

 imag

-0.15

 ball

-0.14

ents

-0.13

UNT

-0.13

DI

-0.13

faction

-0.13

ajas

-0.13

gow

-0.13

POSITIVE LOGITS

utin

0.16

rosis

0.15

rock

0.14

ÙĪØ«

0.14

wick

0.14

ilst

0.14

IDO

0.14

åı¸

0.14

zl

0.14

skip

0.14

Activations Density 0.024%

terms related to software building and project management processes

No Comments

No Known Activations