INDEX

Explanations

references to transportation networks and railways

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Defense

-0.17

ruk

-0.17

ancies

-0.15

 Defense

-0.15

eva

-0.14

apixel

-0.13

atura

-0.13

OrFail

-0.13

amon

-0.13

ANC

-0.13

POSITIVE LOGITS

å¾®è½¯éĽħé»ĳ

0.15

Ð°ÑĢÐ¾Ð²

0.13

umont

0.13

arf

0.13

 Sociology

0.13

 gens

0.13

msp

0.13

 united

0.13

ahr

0.12

irl

0.12

Activations Density 0.010%

references to transportation networks and railways

No Comments

No Known Activations