INDEX

Explanations

references to nuclear energy and weapons

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

ivan

-0.18

ens

-0.15

ag

-0.15

 Bale

-0.14

PLICATION

-0.14

YLES

-0.14

aget

-0.14

akin

-0.13

Alive

-0.13

arde

-0.13

POSITIVE LOGITS

/MIT

0.17

rej

0.16

facet

0.15

acha

0.15

baum

0.15

åĦĢ

0.14

arter

0.14

 Gauge

0.14

Topology

0.14

Ð°ÑĤÐ¾ÑĢ

0.14

Activations Density 0.006%

references to nuclear energy and weapons

No Comments

No Known Activations