INDEX

Explanations

statements about knowledge, belief, and evidence related to actions and events

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

.abstract

-0.16

andard

-0.14

PLL

-0.14

Éµ

-0.13

æĻ

-0.13

 Lang

-0.13

yla

-0.13

ãĥ©ãĥ³

-0.13

rello

-0.13

ulings

-0.13

POSITIVE LOGITS

usercontent

0.14

HORT

0.14

ãĥ£

0.14

ucene

0.14

UNET

0.14

enso

0.14

WARDS

0.13

INET

0.13

GINE

0.13

èķ

0.13

Activations Density 0.181%

statements about knowledge, belief, and evidence related to actions and events

No Comments

No Known Activations