INDEX

Explanations

references to notable people and their professional achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Hayden

-0.18

 Lindsay

-0.18

indsay

-0.17

yon

-0.16

 Bach

-0.16

 Vaughan

-0.16

inka

-0.15

 Lauren

-0.15

SEN

-0.15

 Leeds

-0.15

POSITIVE LOGITS

 Jerry

1.11

Jerry

1.02

Jer

0.94

jer

0.93

Jer

0.92

jer

0.81

 Jerome

0.71

 Jeremiah

0.70

 Jersey

0.69

 jerk

0.67

Activations Density 0.034%

references to notable people and their professional achievements

No Comments

No Known Activations