INDEX

Explanations

mentions of the name "Graham" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

chia

-0.17

ardo

-0.16

hte

-0.15

brig

-0.15

brahim

-0.15

resident

-0.15

haul

-0.15

 Gratuit

-0.14

/stdc

-0.14

Zuk

-0.14

POSITIVE LOGITS

nesty

0.24

stown

0.20

pton

0.19

matic

0.19

 Greene

0.18

ame

0.18

sville

0.18

onium

0.16

ite

0.16

ns

0.15

Activations Density 0.007%

mentions of the name "Graham" in various contexts

No Comments

No Known Activations