INDEX

Explanations

terms related to individual actions or separateness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ÑĢÐµÐ¼

-0.16

 resp

-0.15

baum

-0.14

 possibilities

-0.14

chi

-0.14

uster

-0.13

DIG

-0.13

icker

-0.13

POSITIVE LOGITS

_codegen

0.16

culate

0.16

.promise

0.16

 isolation

0.15

iators

0.15

perms

0.15

/owl

0.14

 isolate

0.14

 separat

0.14

:numel

0.14

Activations Density 0.013%

terms related to individual actions or separateness

No Comments

No Known Activations