INDEX

Explanations

references to literary works and characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

æ¼

-0.16

ÙĦÙģ

-0.15

elem

-0.15

etur

-0.15

dna

-0.14

leur

-0.14

abi

-0.14

esty

-0.14

.socket

-0.14

.Access

-0.14

POSITIVE LOGITS

 exact

0.16

ials

0.15

iana

0.14

Ø±ÙĪØ¨

0.14

ëį

0.14

orc

0.13

à¸§à¸ģ

0.13

hread

0.13

ertino

0.13

tob

0.13

Activations Density 0.028%

references to literary works and characters

No Comments

No Known Activations