INDEX

Explanations

the name "Bron" and variations of it, likely referencing a specific entity or subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

resse

-0.23

vala

-0.15

-regexp

-0.15

ledged

-0.15

rete

-0.15

ropolis

-0.15

æĿ

-0.14

tm

-0.14

rega

-0.14

POSITIVE LOGITS

islav

0.25

zed

0.24

wyn

0.23

chod

0.22

chos

0.20

chi

0.20

zing

0.20

sted

0.20

chio

0.18

 Suche

0.18

Activations Density 0.007%

the name "Bron" and variations of it, likely referencing a specific entity or subject

No Comments

No Known Activations