INDEX

Explanations

descriptive language related to quality and characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.16

à¥ĩà¤ľ

-0.16

no

-0.15

icie

-0.15

-0.14

rix

-0.14

nde

-0.14

 fake

-0.14

ten

-0.14

POSITIVE LOGITS

ëį°

0.16

itarian

0.15

nid

0.15

__$

0.14

.Glide

0.14

ICLE

0.14

.builders

0.13

.mybatisplus

0.13

agnost

0.13

ONES

0.13

Activations Density 0.274%

descriptive language related to quality and characteristics

No Comments

No Known Activations