INDEX

Explanations

proper names, particularly those associated with personal relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ofs

-0.15

abcdefghijklmnop

-0.15

å°İ

-0.15

cab

-0.14

erras

-0.14

zi

-0.14

wins

-0.14

abcdefghijkl

-0.14

]={↵

-0.14

 Knot

-0.14

POSITIVE LOGITS

åģ¥

0.15

HT

0.14

Tar

0.14

_transient

0.14

ndon

0.14

 meiden

0.13

leans

0.13

 MatSnackBar

0.13

 hopping

0.13

eyse

0.13

Activations Density 0.255%

proper names, particularly those associated with personal relationships

No Comments

No Known Activations