INDEX

Explanations

phrases relating to equivalence and comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yon

-0.14

ella

-0.14

 ãĢĪ

-0.14

 Ramos

-0.14

olith

-0.14

eron

-0.14

_simps

-0.14

oret

-0.13

ÙĬØ¬

-0.13

yms

-0.13

POSITIVE LOGITS

 Equivalent

0.18

ypsy

0.16

asti

0.15

 equivalent

0.15

 GOODMAN

0.15

iez

0.15

metatable

0.15

ivalent

0.15

onymous

0.14

Activations Density 0.015%

phrases relating to equivalence and comparison

No Comments

No Known Activations