INDEX

Explanations

phrases related to personal actions and experiences in various contexts

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

auen

-0.15

 Victory

-0.15

/o

-0.14

ãĥįãĥ«

-0.13

FLAG

-0.13

-hop

-0.13

hy

-0.13

oa

-0.13

 victory

-0.13

NP

-0.13

POSITIVE LOGITS

Calibri

0.15

bew

0.14

onio

0.14

ÑĥÑĢÐµ

0.14

 Shutterstock

0.14

.outer

0.14

apot

0.14

bbe

0.13

.assertIs

0.13

ulace

0.13

Activations Density 0.099%

phrases related to personal actions and experiences in various contexts

No Comments

No Known Activations