INDEX

Explanations

references to naval vessels, specifically submarines and ships

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

coln

-0.16

gre

-0.15

MSM

-0.14

Cheap

-0.14

ascus

-0.14

 Laden

-0.14

erno

-0.13

icie

-0.13

dau

-0.13

ifax

-0.13

POSITIVE LOGITS

boat

0.16

Î²Î¬

0.16

uth

0.16

ouv

0.15

OCI

0.15

bons

0.14

uvre

0.14

esse

0.14

plot

0.14

SND

0.14

Activations Density 0.002%

references to naval vessels, specifically submarines and ships

No Comments

No Known Activations