INDEX

Explanations

recognition and understanding of knowledge or awareness in various contexts

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

asz

-0.16

nga

-0.16

ade

-0.15

inh

-0.15

ll

-0.15

inho

-0.15

oya

-0.14

.fb

-0.14

 chap

-0.14

ese

-0.14

POSITIVE LOGITS

 ráº±ng

0.14

GestureRecognizer

0.14

UnderTest

0.14

astos

0.14

 bergen

0.14

íĨ¡

0.14

0.13

ÑģÑĮ

0.13

ENCHMARK

0.13

Activations Density 0.081%

recognition and understanding of knowledge or awareness in various contexts

No Comments

No Known Activations