INDEX

Explanations

word frequency and usage in relation to personal experiences or expressions of opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ercul

-0.15

Contracts

-0.15

agus

-0.15

drag

-0.14

lesh

-0.14

onces

-0.14

imers

-0.14

led

-0.14

pheres

-0.14

agli

-0.14

POSITIVE LOGITS

INAL

0.15

mention

0.15

Ð¾Ð²Ð¸

0.14

 dici

0.14

URN

0.14

.precision

0.14

akt

0.14

acho

0.14

 toggle

0.13

 Donovan

0.13

Activations Density 0.000%

word frequency and usage in relation to personal experiences or expressions of opinion

No Comments

No Known Activations