INDEX

Explanations

references to "things" or "stuff" in a context that implies their significance or relevance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ERVE

-0.15

ITES

-0.15

aptor

-0.15

jective

-0.14

ipur

-0.14

doch

-0.14

ensis

-0.14

usercontent

-0.14

licht

-0.14

itz

-0.14

POSITIVE LOGITS

 happening

0.20

ToDo

0.19

 happens

0.18

strup

0.17

ummy

0.17

 happened

0.17

/people

0.16

 happen

0.16

yi

0.15

 Happ

0.15

Activations Density 0.154%

references to "things" or "stuff" in a context that implies their significance or relevance

No Comments

No Known Activations