INDEX

Explanations

specific terms that introduce or emphasize details or nuances in a discussion or argument

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

eph

-0.15

.trace

-0.15

imilar

-0.15

_PIX

-0.15

inson

-0.14

çĮĽ

-0.14

phem

-0.14

paragus

-0.14

esus

-0.14

pedo

-0.14

POSITIVE LOGITS

 Overnight

0.15

 specifically

0.15

-speaking

0.14

TTY

0.14

pps

0.14

amb

0.13

ÏĩÎµ

0.13

 Yoshi

0.13

datable

0.13

anners

0.13

Activations Density 0.028%

specific terms that introduce or emphasize details or nuances in a discussion or argument

No Comments

No Known Activations