INDEX

Explanations

phrases indicating expectations and evaluations of capability

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

ankind

-0.15

ucs

-0.14

pap

-0.14

Handles

-0.14

anoia

-0.14

 Hardy

-0.13

 Fraser

-0.13

ÑĢÐ¾Ñĩ

-0.13

washing

-0.13

.ef

-0.13

POSITIVE LOGITS

rone

0.15

 dial

0.15

 Dial

0.15

_FACTORY

0.14

Normalization

0.14

´Ģ

0.14

Invoke

0.14

MMC

0.14

shan

0.13

.nano

0.13

Activations Density 0.031%

phrases indicating expectations and evaluations of capability

No Comments

No Known Activations