INDEX

Explanations

terminology and phrases related to medical diagnoses and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

EDGE

-0.16

typings

-0.15

rite

-0.15

ÑĪÐ¸ÑĢ

-0.15

 allegedly

-0.15

çıł

-0.14

Convention

-0.14

drs

-0.14

_:*

-0.14

 retaining

-0.14

POSITIVE LOGITS

REP

0.18

´Ī

0.15

eyJ

0.15

uis

0.14

ances

0.14

ey

0.14

egra

0.14

fg

0.14

_likes

0.14

Jew

0.14

Activations Density 0.012%

terminology and phrases related to medical diagnoses and treatments

No Comments

No Known Activations