INDEX

Explanations

occurrences of specific numerical figures and place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

iry

-0.16

Ì£

-0.15

iesel

-0.15

egg

-0.15

 sounding

-0.14

rpc

-0.14

_AC

-0.14

 å·

-0.14

pls

-0.13

POSITIVE LOGITS

nop

0.15

 bekl

0.14

 McMahon

0.14

iman

0.14

EIF

0.13

 Rapid

0.13

NSS

0.13

pekt

0.13

TeV

0.13

meric

0.13

Activations Density 0.009%

occurrences of specific numerical figures and place names

No Comments

No Known Activations