INDEX

Explanations

conditional phrases that imply dependency or variability based on context

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

offs

-0.15

-scripts

-0.15

ters

-0.15

mare

-0.14

charger

-0.14

 pacing

-0.14

vang

-0.14

minute

-0.14

tur

-0.14

ÎµÎ²

-0.14

POSITIVE LOGITS

fy

0.15

iggs

0.15

otte

0.15

ersh

0.15

eral

0.15

Vul

0.15

vi

0.15

agrid

0.15

iyon

0.15

ichtet

0.15

Activations Density 0.016%

conditional phrases that imply dependency or variability based on context

No Comments

No Known Activations