INDEX

Explanations

concepts related to political authority and symbolic actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ForKey

-0.15

 suspicious

-0.14

mania

-0.14

 ÙĤØ§Ø¨

-0.14

aur

-0.14

ipes

-0.13

TEM

-0.13

inkel

-0.13

 addCriterion

-0.13

POSITIVE LOGITS

 statement

0.43

symbol

0.42

 symbol

0.41

statement

0.38

 symbols

0.37

 symbolic

0.36

 symbolism

0.36

Symbol

0.35

 Symbol

0.35

 statements

0.34

Activations Density 0.181%

concepts related to political authority and symbolic actions

No Comments

No Known Activations