INDEX

Explanations

references to various types of seating arrangements and their contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

OffsetTable

-0.18

gap

-0.15

 Circuit

-0.15

lems

-0.14

toa

-0.14

é£¯

-0.14

lage

-0.14

ÑĢÑĥÐ½

-0.13

StrictEqual

-0.13

 Modules

-0.13

POSITIVE LOGITS

 chair

0.65

 Chair

0.57

-chair

0.55

chair

0.54

 chairs

0.54

Chair

0.52

 Chairs

0.50

 chairman

0.43

æ¤ħ

0.41

 Chairman

0.40

Activations Density 0.085%

references to various types of seating arrangements and their contexts

No Comments

No Known Activations