INDEX

Explanations

references to service offerings and photography

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

æ´²

-0.13

 legend

-0.13

iera

-0.13

_fh

-0.12

cstdio

-0.12

burg

-0.12

eder

-0.12

POSITIVE LOGITS

etc

0.16

 ÑĤÐ¾ÑīÐ¾

0.16

etc

0.14

ombo

0.14

_BLOCKS

0.14

 Ekon

0.14

ãģıãĤĵ

0.14

.trailing

0.13

ujet

0.13

atego

0.13

Activations Density 0.312%

references to service offerings and photography

No Comments

No Known Activations