INDEX

Explanations

references to historical or literary subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

bject

-0.16

_hop

-0.15

hong

-0.15

amber

-0.14

ADOR

-0.14

 Latter

-0.14

orr

-0.14

adr

-0.14

andin

-0.14

Ã¨res

-0.13

POSITIVE LOGITS

gaard

0.16

.UUID

0.14

 Gilles

0.13

 Ã¡n

0.13

 accessed

0.13

 Stam

0.13

æĪĸèĢħ

0.13

åĪĴ

0.13

SION

0.13

VT

0.13

Activations Density 0.489%

references to historical or literary subjects

No Comments

No Known Activations