INDEX

Explanations

references to language and grammatical structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

translated

-0.16

Translated

-0.16

zilla

-0.15

 ä»»

-0.15

 smoke

-0.14

 translated

-0.14

 INTERVAL

-0.14

eria

-0.14

à¸Ļà¸²à¸¡

-0.14

Php

-0.14

POSITIVE LOGITS

 regional

0.21

 spoken

0.19

 dialect

0.19

 Regional

0.18

 variants

0.16

 senses

0.16

-spe

0.16

Regional

0.16

spoken

0.16

_REGION

0.15

Activations Density 0.041%

references to language and grammatical structures

No Comments

No Known Activations