INDEX

Explanations

occurrences of the word "Fort" as well as associated phrases and names

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

usercontent

-0.15

 tslint

-0.15

halb

-0.14

agent

-0.14

 Shank

-0.14

amba

-0.14

á»ī

-0.13

ÂŃi

-0.13

 Mare

-0.13

urovision

-0.13

POSITIVE LOGITS

sWith

0.16

ughters

0.16

allas

0.14

lies

0.14

.logging

0.14

ros

0.14

CRYPT

0.14

 aggressively

0.14

uet

0.14

Activations Density 0.004%

occurrences of the word "Fort" as well as associated phrases and names

No Comments

No Known Activations