INDEX

Explanations

actions related to theft or removal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÏģÏį

-0.15

wy

-0.15

estone

-0.14

ognition

-0.14

kie

-0.14

stant

-0.14

LocalizedString

-0.14

è¡¡

-0.14

sto

-0.14

ÑĢÑİ

-0.13

POSITIVE LOGITS

ikan

0.18

0.16

Liv

0.15

Liv

0.15

.snp

0.15

endale

0.15

 khá»ıi

0.15

ilated

0.15

åı·

0.14

 Casc

0.14

Activations Density 0.089%

actions related to theft or removal

No Comments

No Known Activations