INDEX

Explanations

references to a specific hospital or medical facility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

IDA

-0.16

âĢ¦↵↵↵

-0.16

uraa

-0.15

licity

-0.15

uzzi

-0.15

/ss

-0.15

ÙĦØ§ØŃ

-0.15

alom

-0.14

nesc

-0.14

erif

-0.14

POSITIVE LOGITS

ando

0.17

GT

0.17

MLE

0.16

nummer

0.16

apl

0.16

0.15

ConnectionFactory

0.15

ITHER

0.15

ry

0.15

é¡¹

0.15

Activations Density 0.010%

references to a specific hospital or medical facility

No Comments

No Known Activations