INDEX

Explanations

references to executions and related violent acts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çŁ¢

-0.16

xsi

-0.14

olie

-0.14

ê¹

-0.13

 congress

-0.13

}elseif

-0.13

ãĥ¬ãĥ¼

-0.13

Quit

-0.13

 pigeon

-0.13

leftright

-0.13

POSITIVE LOGITS

estar

0.17

undi

0.15

Ð´Ñı

0.15

usp

0.14

odash

0.14

immer

0.14

Î¬Î½ÏĦÎ±

0.14

ÑĩÐ°

0.14

arrant

0.14

ãĥĥãĥĪ

0.14

Activations Density 0.047%

references to executions and related violent acts

No Comments

No Known Activations