INDEX

Explanations

references to quality descriptors and assessments 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ãĥĩãĤ£ãĤ¢

-0.16

oppable

-0.14

 Alexis

-0.14

ont

-0.14

sten

-0.14

ÑĩÐ°

-0.13

æŁĲ

-0.13

pz

-0.13

parency

-0.13

POSITIVE LOGITS

ones

0.18

cus

0.15

zing

0.15

Ã¤hlen

0.15

annis

0.15

ETO

0.14

 honey

0.14

akin

0.14

Ã¤hr

0.14

aines

0.14

Activations Density 0.244%

references to quality descriptors and assessments in various contexts

No Comments

No Known Activations