INDEX

Explanations

references to specific locations and their associated attributes or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

elper

-0.15

å¡ļ

-0.15

iq

-0.15

immel

-0.15

éĻ£

-0.14

izont

-0.14

ÑħÑĥ

-0.14

erca

-0.14

ł

-0.14

POSITIVE LOGITS

å¤§åħ¨

0.15

#ac

0.15

ryn

0.15

 Russ

0.14

ssize

0.14

è´¨

0.14

ãĥ¼ãĥį

0.14

Gos

0.14

aos

0.14

]int

0.13

Activations Density 0.032%

references to specific locations and their associated attributes or services

No Comments

No Known Activations