INDEX

Explanations

phrases that express concepts related to perception or characteristics of life

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

aket

-0.16

ry

-0.15

prof

-0.15

asha

-0.15

-CN

-0.14

indir

-0.13

automation

-0.13

PACE

-0.13

bsp

-0.13

asar

-0.13

POSITIVE LOGITS

Ð»Ð°Ð´Ð°

0.15

onom

0.15

 AppModule

0.15

osos

0.14

oya

0.14

EMA

0.14

 Simmons

0.14

 Accountability

0.14

cus

0.14

anlÄ±k

0.14

Activations Density 0.012%

phrases that express concepts related to perception or characteristics of life

No Comments

No Known Activations