INDEX

Explanations

occurrences of the word "Mor."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

strap

-0.18

Øª

-0.17

entina

-0.17

enza

-0.16

urn

-0.16

ourt

-0.16

edral

-0.15

incinn

-0.15

etti

-0.15

apse

-0.15

POSITIVE LOGITS

rell

0.21

Mor

0.20

ris

0.19

Mor

0.19

MOR

0.19

mor

0.18

occan

0.18

phia

0.18

 Morris

0.17

ality

0.17

Activations Density 0.006%

occurrences of the word "Mor."

No Comments

No Known Activations