INDEX

Explanations

mentions of the name "Kwame."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ainen

-0.17

pare

-0.16

uctions

-0.15

ozo

-0.15

avenous

-0.14

_endian

-0.14

udit

-0.14

 olds

-0.14

 Tort

-0.14

lep

-0.14

POSITIVE LOGITS

ame

0.18

adr

0.18

ality

0.16

esi

0.15

kus

0.14

RGBA

0.14

ak

0.14

Memcpy

0.14

pecially

0.14

ÄĻk

0.14

Activations Density 0.007%

mentions of the name "Kwame."

No Comments

No Known Activations