INDEX

Explanations

terms related to software distribution and licensing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

chio

-0.17

 bias

-0.17

erton

-0.16

less

-0.16

bach

-0.16

.bias

-0.14

elas

-0.14

 Sovere

-0.14

elsen

-0.14

.Cast

-0.14

POSITIVE LOGITS

stad

0.18

amble

0.17

agus

0.16

Ð²ÑĢÐ¾Ð¿

0.16

zp

0.15

ÏĦÏī

0.14

Hin

0.14

pak

0.14

ctrine

0.14

Activations Density 0.003%

terms related to software distribution and licensing

No Comments

No Known Activations

terms related to software distribution and licensing

No Comments

No Known Activations