INDEX

Explanations

references to medical procedures and diagnostics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

iT

-0.16

 biom

-0.14

 scenarios

-0.14

 Accord

-0.14

 scenario

-0.14

 trajectories

-0.14

 transitioning

-0.14

 anyways

-0.14

 scaffold

-0.14

bos

-0.14

POSITIVE LOGITS

 USSR

0.17

0.16

0.15

EGA

0.15

phem

0.15

Î¬Ïģ

0.14

æĵį

0.14

ãĤ·ãĥ¼

0.14

Activations Density 0.093%

references to medical procedures and diagnostics

No Comments

No Known Activations