INDEX

Explanations

references to personal narratives and historical documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ä¹ĥ

-0.14

ATUS

-0.14

hav

-0.14

 converged

-0.13

jak

-0.13

ÄħÅ¼

-0.13

 alleged

-0.13

Hav

-0.13

hed

-0.13

 Lage

-0.12

POSITIVE LOGITS

 entries

0.17

 Routine

0.16

æĿŁ

0.15

NX

0.15

Entries

0.14

entries

0.14

 richest

0.14

 zengin

0.14

odate

0.14

ãĥ¬ãĥ³

0.14

Activations Density 0.019%

references to personal narratives and historical documents

No Comments

No Known Activations